metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ucf101-subset
results: []
videomae-base-finetuned-ucf101-subset
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.0235
- Accuracy: 0.2575
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 480
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.2682 | 0.0646 | 31 | 4.2493 | 0.0033 |
| 4.2584 | 1.0646 | 62 | 4.2434 | 0.0134 |
| 4.2518 | 2.0646 | 93 | 4.2246 | 0.0167 |
| 4.2445 | 3.0646 | 124 | 4.2208 | 0.0067 |
| 4.2272 | 4.0646 | 155 | 4.2230 | 0.0100 |
| 4.205 | 5.0646 | 186 | 4.2111 | 0.0234 |
| 4.1238 | 6.0646 | 217 | 4.1112 | 0.0368 |
| 3.9136 | 7.0646 | 248 | 3.8530 | 0.0736 |
| 3.6241 | 8.0646 | 279 | 3.6734 | 0.1171 |
| 3.3103 | 9.0646 | 310 | 3.5261 | 0.1070 |
| 3.0981 | 10.0646 | 341 | 3.3860 | 0.1639 |
| 2.8216 | 11.0646 | 372 | 3.1791 | 0.2140 |
| 2.6108 | 12.0646 | 403 | 3.1618 | 0.2441 |
| 2.598 | 13.0646 | 434 | 3.0793 | 0.2341 |
| 2.5023 | 14.0646 | 465 | 3.0194 | 0.2575 |
| 2.513 | 15.0312 | 480 | 3.0668 | 0.2375 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0